How LLMs and coding tools work8 min read

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, Denny Zhou · 2022 · NeurIPS 2022 · Advances in Neural Information Processing Systems 35

Show a model examples that include the intermediate steps, not just the answer, and its accuracy on multi-step problems jumps — but only if the model is large enough.

Read the paper ↗

The short version

→A chain of thought is a series of intermediate reasoning steps written out before the final answer.
→Putting eight such worked examples in the prompt took a 540B-parameter model to state-of-the-art accuracy on the GSM8K grade-school maths benchmark, beating a fine-tuned GPT-3 with a separate verifier.
→The gain is an emergent property of scale: on small models chain-of-thought prompting helps little and can hurt.
→It costs output tokens. Reasoning is generated text, and generated text is the expensive half of your bill.

Subscription

The Library

Everything running a software business asks of you and none of it is code: onboarding that activates, churn you can actually see coming, marketing with no budget, SEO that finds buyers, and the AI-plus-Ahrefs workflow for writing the blog that feeds it. One new playbook a week, plus the whole archive from day one.

$9/ month · cancel any time

✓A new playbook every week — onboarding, churn, growth, SEO, content
✓The full back catalogue the moment you join, not drip-fed
✓Vendor explainers: Stripe, Supabase, Resend, Vercel, the AI APIs
✓The research shelf — real papers, decoded, on learning and on LLMs
✓One email when a new one lands, off by default in one click
✓Cancel any time; you keep reading to the end of the month

first — it takes ten seconds.

No card is asked for yet — the subscription is recorded and really opens your account. See all plans →